© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14590
    Prev
    Next
    INDEX
    Explanations

    sentences or clauses starting with "there is/are"

    oai_token-act-pair · gemini-2.0-flash

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.88
     Jefus
    -0.86
     Efq
    -0.77
     Houſe
    -0.77
     Majefty
    -0.76
     Anſ
    -0.75
     uſe
    -0.74
    Билгалдахарш
    -0.74
     houſe
    -0.73
     وتسجيلات
    -0.71
    POSITIVE LOGITS
     lies
    0.67
     lie
    0.55
    <bos>
    0.54
     most
    0.51
     comes
    0.49
     rests
    0.48
    égard
    0.45
     really
    0.45
     is
    0.44
     
    0.44
    Activations Density 0.313%

    No Known Activations